© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53156
    Prev
    Next
    INDEX
    Explanations

    ‘quotes’ or apostrophes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    panse
    -0.11
    arters
    -0.11
    趸
    -0.11
    æ¹Ħ
    -0.10
    æµĥ
    -0.10
    ä¸ķ
    -0.10
    å¼Ī
    -0.10
    .Cursors
    -0.10
    .jackson
    -0.10
    建æĪIJåIJİ
    -0.10
    POSITIVE LOGITS
    èĩªå·±
    0.10
    éĤ£äºĽ
    0.10
    å±ŀäºİèĩªå·±
    0.10
     a
    0.10
    èĩªå·±çļĦ
    0.10
    èĩªå·±åĸľæ¬¢
    0.10
    éĤ£ç§į
    0.10
    æŁIJç§į
    0.09
    èĩªèº«çļĦ
    0.09
    è¿Ļæł·ä¸Ģ个
    0.09
    Activations Density 0.147%

    No Known Activations